• 한국정보과학회논문지:시스템및이론
• /
• 제31권10호
• /
• pp.575-587
• /
• 2004

본 논문은 여러 분야에서 활용될 수 있는 향상된 고속 Expectation-Maximization(FEM) 알고리즘을 제안한다. 첫째, EM의 초기값 설정의 방법으로 많이 사용되고 있는 클러스터링 기법인 K-means의 문제점을 해결하여 개선된 EM의 초기값 선정에 적용하였다. 이것은 기존 K-means 알고리즘에서 임의로 지정하던 랜덤한 초기값 선정을, 데이타 분포 특성을 이용한 균등 분할법을 사용하여 EM의 초기값 문제를 해결하였다. 둘째, EM 과정의 핵심을 이루는 후행 확률(Posterior)의 의미를 부각하여 최대 가능성 후행 확률(Maximum Likelihood Posterior: MLP)과정을 적용하였다. 최종적으로, 본 논문에서 제안한 고속 EM알고리즘(FEM)은 근본적으로 해결하기 못했던 기존의 EM 초기치 선정과 수렴에 대한 문제점을 개선함으로써, EM 알고리즘의 특성을 극대화하는 방향으로 상대적으로 마른 수렴과 향상된 결과를 가져온다. 제안된 알고리즘의 객관적 타당성을 위해 기존의 방법과 제안된 방법에 의한 시뮬레이션의 결과를 여러 데이타들을 가지고 비교 분석하여 제안한 알고리즘의 우수성을 입증하였다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제21권3호
• /
• pp.331-339
• /
• 2008

The genetic structure and diversity of 15 Chinese indigenous chicken breeds was investigated using 29 microsatellite markers. The total number of birds examined was 542, on average 36 birds per breed. A total of 277 alleles (mean number 9.55 alleles per locus, ranging from 2 to 25) was observed. All populations showed high levels of heterozygosity with the lowest estimate of 0.440 for the Gushi chickens, and the highest one of 0.644 observed for Wannan Three-yellow chickens. The global heterozygote deficit across all populations (FIT) amounted to 0.180 (p<0.001). About 16% of the total genetic variability originated from differences between breeds, with all loci contributing significantly to this differentiation. An unrooted consensus tree was constructed using the Neighbour-Joining method and pair-wise distances based on marker estimated kinships. Two main groups were found. The heavy-body type populations grouped together in one cluster while the light-body type populations formed the second cluster. The STRUCTURE software was used to assess genetic clustering of these chicken breeds. Similar to the phylogenetic analysis, the heavy-body type and light-body type populations separated first. Clustering analysis provided an accurate representation of the current genetic relations among the breeds. Remarkably similar breed rankings were obtained with all methods.

• 한국지능시스템학회논문지
• /
• 제2권3호
• /
• pp.29-39
• /
• 1992

We investigate a systematic design procedure of automatic rule generation of fuzzy logic based controllers for highly nonlinear dynamic systems such as an engine dynamic modle. By "automatic rule generation" we mean autonomous clustering or collection of such meaningful transitional relations from one conditional subspace to another. During the design procedure, we also consider optimaly control strategies such as minimum squared error, near minimum time, minimum energy or combined performance critiera. Fuzzy feedback control systems designed by our method have the properties of closed-loop stability, robustness under parameter variabitions, and a certain degree of optimality. Most of all, the main advantage of the proposed approach is that reliability can be potentially increased even if a large grain of uncertainty is involved within the control system under consideration. A numerical example is shown in which we apply our strategic fuzzy controller dwsign to a highly nonlinear model of engine idling speed control.d control.

• 한국물환경학회지
• /
• 제28권2호
• /
• pp.202-212
• /
• 2012

Due to the deterioration of water supply network and the deficiency of raw water, the water utility of local governments have performed various projects to improve their revenue water ratio. However, it is very difficult to estimate the cost for maintaining the revenue water ratio at higher level after completing the project, because local governments have different conditions affecting the operating and maintenance cost of water supply network. The purpose of this study is to present a procedure to estimate the operating and maintenance cost required to maintain the target revenue water ratio of the water supply network. For this purpose, we estimated the cost used only for operation and maintenance of water supply network of 164 local governments with the aid of K-Mean Clustering Analysis and the data from 40 representative local governments. Then, the regression analysis was performed to find relationship between revenue water ratio and the operating and maintenance cost with two different data sets generated by two classification methods; the first method classifies the local governments by means of k-means clustering, and the other classifies the local governments according to the index standardized by the operating and maintenance cost per unit length of water mains per revenue water ratio. The results shows that the method based on the index standardized by the cost and revenue water ratio of each government produces more reliable results for finding regression equations between revenue water ratio and the operating and maintenance cost only for water supply network. The estimated regression equations for each group can be used to estimate the cost required to keep the target revenue water ratio of the local government.

• Molecular & Cellular Toxicology
• /
• 제2권2호
• /
• pp.126-133
• /
• 2006

Thioacetamide (TA) is well known hepatotoxic and hepatocarcinogenic agent. TA also diminishes the contents of hepatic cytochrome P450 and inhibits the enzyme activity of the hepatic mixed function oxidases. TA metabolite, thioacetamide-s-oxide, is further transformed into a still unknown highly reactive metabolite that binds to macromolecules. In this study, we focused on TA-induced gene expression at hepatotoxic dose. Mice were exposed to two levels (5 mg/kg or 50 mg/kg i.p.) of TA, sampled at 6 or 24 h, and hepatic gene expression levels were determined to evaluate dose and time dependent changes. We evaluated hepatotoxicity by serum AST and ALT level and histopathological observation. Mean serum activities of the liver leakage enzymes, AST and ALT, were slightly increased compare to control. H & E and PAS evaluation of stained liver sections revealed TA-associated histopathological finding in mice. Centrilobular eosinophilic degeneration was observed at high dose-treated mice group. Hepatic gene expression was analyzed by QT clustering. Clustering of high dose-treated samples with TA-suggests that gene expressional changes could be associated from toxicity as measured by traditional biomarkers in this acute study.

• 전기화학회지
• /
• 제14권1호
• /
• pp.9-15
• /
• 2011

The composite membranes comprising of sulfonated polymers as matrix and ionic liquids as ion-conducting medium in replacement of water are studied to investigate the effect of annealing of the sulfonated polymers. The polymeric membranes are prepared on recast Nafion containing the ionic liquid, 1-ethyl-3-methylimidazolium tetrafluoroborate ($EMIBF_4$). The composite membranes are characterized by thermogravitational analyses, ion conductivity and small-angle X-ray scattering. The composite membranes annealed at $190^{\circ}C$ for 2 h after the fixed drying step showed better ionic conductivity, but no significant increase in thermal stability. The mean Bragg distance between the ionic clusters, which is reflected in the position of the ionomer peak (small-angle scattering maximum), is larger in the annealed composite membranes containing $EMIBF_4$ than the non-annealed ones. It might have been explained to be due to the different level of ion-clustering ability of the hydrophilic parts (i.e., sulfonic acid groups) in the non- and annealed polymer matrix. In addition, the ionic conductivity of the membranes shows higher for the annealed composite membranes containing $EMIBF_4$. It can be concluded that the annealing of the composite membranes containing ionic liquids due to an increase in ion-clustering ability is able to bring about the enhancement of ionic conductivity suitable for potential use in proton exchange membrane fuel cells (PEMFCs) at medium temperatures ($150-200^{\circ}C$) in the absence of external humidification.

• 응용통계연구
• /
• 제36권1호
• /
• pp.49-62
• /
• 2023

급속적으로 비중이 증가하고 있는 태양광 에너지는 지속적인 개발 및 투자가 이루어지고 있다. 신재생에너지 정책인 그린뉴딜과 가정용 태양광 패널의 설치가 증가함에 따라 국내 태양광 에너지 보급이 점차 확대되어 그에 맞추어 발전량의 정확한 수요 예측 연구가 활발하게 진행되고 있는 시점이다. 또한, 일사량 예측이 발전량 수요 예측에 가장 영향을 미치는 요소로 작용하고 있다는 점에서 일사량 예측의 중요성을 파악하였다. 덧붙여, 본 연구는 선행 연구들에서 사용되지 않은 중기예보 기상 데이터를 활용하여 일사량 예측을 하고자 하였다는 점에서 가장 큰 차이점을 확인할 수 있다. 본 논문에서는 서울, 인천, 수원, 춘천, 대구, 대전의 총 여섯 지역의 태양광 일사량 예측을 위하여 다중선형회귀모형, KNN, Random Forest 그리고 SVR 모형과 클러스터링 기법인 K-means 기법을 결합한 후, 클러스터별 확률밀도함수를 계산하여 시간별 일사량 예측을 진행하고자 하였다. 중기예보 데이터를 사용하기 전, 모형 예측 결과를 비교하기 위한 지표로서 MAE (mean absolute error)와 RMSE (root mean squared error)를 사용하였다. 데이터는 2017년 3월 1일부터 2022년 2월 28일까지의 시간별 원 관측 데이터를 중기예보 데이터 양식에 맞추어 일별 데이터로 변환하였다. 모형의 예측 성능 비교 결과, Random Forest로 일별 일사량을 예측한 후, K-means 클러스터링으로 기후요인이 유사한 날짜들을 분류한 뒤 클러스터별 일사량의 확률밀도함수를 계산하여 시간별 일사량 예측값을 나타낸 방법이 가장 우수한 성능을 보였다. 또한 이 방법론을 이용하여 중기예보 데이터에 모형 적합 후, 예측 결과를 확인하였을 때, 일자별로 예측 오류가 상승하는 것을 확인할 수 있었다. 이는 중기예보 기상데이터의 예측 오류로 인한 것으로 보인다. 향후 연구에서는 중기예보 데이터에서 활용할 수 있는 기상요인 중, 강수 여부와 같은 외생 변수를 추가하거나 시계열 클러스터링 기법을 적용한 연구가 이루어져야할 것으로 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권8호
• /
• pp.2833-2850
• /
• 2014

This paper proposes a novel framework for traffic video classification based on chaotic features. First, each pixel intensity series in the video is modeled as a time series. Second, the chaos theory is employed to generate chaotic features. Each video is then represented by a feature vector matrix. Third, the mean shift clustering algorithm is used to cluster the feature vectors. Finally, the earth mover's distance (EMD) is employed to obtain a distance matrix by comparing the similarity based on the segmentation results. The distance matrix is transformed into a matching matrix, which is evaluated in the classification task. Experimental results show good traffic video classification performance, with robustness to environmental conditions, such as occlusions and variable lighting.

• Plant Resources
• /
• 제4권3호
• /
• pp.121-129
• /
• 2001

Intraspecific genetic diversity of sixteen accessions of Mogolian Alliums including fifteen species was investigated using randomly amplified polymorphic DNA (RAPD) analysis. Twenty three out of forty primers revealed scorable polymorphism. A total of 440 RAPD markers were generated on the 16 accessions of Mongolian Alliums. Among 440 RAPDs assayed, 439 were polymorphic with a mean polymorphic rate of 99.7%. Unweighted pair-group method using an arithmetic average (UPGMA) cluster analysis using RAPD data separated the 16 Allium accessions into two broad groups at similarity index 0.70. The clustering of the species was closely related with previous classification between A. altaicum and A. fistulosum. In addition, a high genetic similarity was showed between A. cepa and A. tagar.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.364-366
• /
• 2021

본 논문은 비전 기술을 기반으로 RHS 칼라차트를 이용하여 작물의 색채를 측정하는 특성조사기준에 관한 연구를 수행하였다. 다양한 색상을 가진 작물의 색채를 측정하기 위해 시료 채취 후 표준광원 촬영장치 광원 6500K 환경하에 촬영한 영상을 기반으로 분석 위치를 관심영역 선정 후, k-mean clustering을 활용한 세그먼테이션 방법을 통해 대표 RGB 색상을 획득한다. 획득한 RGB 색상과 RHS 칼라차트의 RGB 색상을 유클리디언 거리를 이용하여 최소화하는 RHS 칼라차트 정보를 추정하였다. 7가지 작물 시료에 대해 작물 형질 분석 전문가들이 측정한 결과와 비교 시 전체 평균 △E 5.013의 오차를 결과로 도출하였다.